Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ruchernchong/claude-kit --skill securitygit clone --depth 1 https://github.com/ruchernchong/claude-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ruchernchong/claude-kit/security)<a href="https://agentmods.dev/skills/ruchernchong/claude-kit/security"><img src="https://agentmods.dev/badge/skills/ruchernchong/claude-kit/security/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ruchernchong/claude-kit/security"><img src="https://agentmods.dev/badge/skills/ruchernchong/claude-kit/security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00016 | $0.00550 |
| Opus 5.5 | $0.00006 | $0.00220 |
| Sonnet 5.5 | $0.00003 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
security scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security engineer setting up GitLeaks and running security audits.
Workflow
1. Setup GitLeaks in Husky Pre-commit Hook
Check if GitLeaks is configured in the project's pre-commit hook. If not, set it up.
Detection Steps
- Check if
.husky/directory exists - Check if
.husky/pre-commitcontainsgitleaks
Setup Steps (if GitLeaks is missing)
If .husky/ does not exist:
npx husky init
Add GitLeaks to .husky/pre-commit BEFORE any lint-staged command:
gitleaks protect --staged --verbose
Example .husky/pre-commit with lint-staged:
#!/usr/bin/env sh
. "$(dirname -- "$0")/_/husky.sh"
# Secrets detection - fail fast if secrets found
gitleaks protect --staged --verbose
# Lint staged files
npx lint-staged
If the pre-commit file already exists, insert the gitleaks line before npx lint-staged.
2. Code Security Audit
After ensuring GitLeaks is configured, spawn the security-auditor agent to analyze code:
Use the Task tool with subagent_type: security-auditor to run a security audit on the codebase.
Focus on OWASP Top 10 vulnerabilities, authentication issues, and data protection.
3. Retrospective Git History Scan (Optional)
Only run this step if the user passes --scan-history argument. This is for legacy projects being onboarded to GitLeaks.
gitleaks detect --source . --verbose
Report any secrets found in git history with:
- File path and line number
- Commit where the secret was introduced
- Type of secret detected
- Remediation steps (rotate the secret, use git-filter-repo to remove from history)
Output Format
- GitLeaks Setup Status: Whether hooks were already configured or newly set up
- Security Audit Findings: Results from the security-auditor agent
- History Scan Results (if --scan-history): Any secrets found in git history
Assumptions
- GitLeaks is already installed on the system (
brew install gitleaksor equivalent) - Target projects use Husky + lint-staged (JS/TS stack)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 79 lines · 16 tokens per session scan A 0b5235c317fb
security is a skill published in the GitHub repository ruchernchong/claude-kit (0 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 550 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other skills, from other repositories
wttr-weather
Weather via wttr.in GET (no key). Use for weather/forecast; prefer os.http.request.
jk
Manage Jenkins controllers with jk, including jobs, runs, logs, artifacts, credentials, nodes, queues, and plugins.
engineering-principles
Practical engineering judgement: smallest change, subtract before adding, data structures before logic, idempotent operations, migrate callers then delete. Use when designing, building, or reviewing changes.
financial-analysis
Financial figures done carefully: periods and fiscal calendars, units and currencies, reconciliation, magnitude sanity checks, sourced assumptions. Use for statements, budgets, pricing, and diligence numbers.
scheduling
Scheduling across time zones: confirm times in the attendee's own zone, use IANA zone names, mind DST edges, buffers and calendar etiquette. Use when booking meetings or calls with people in other zones.
writing
Writing that sounds human: strip AI tells (em dashes, filler, hype, tacked-on tricolons), plain language, active voice, reader-first structure. Use when drafting or editing copy, docs, posts, or messages.